Triple

T20868762
Position Surface form Disambiguated ID Type / Status
Subject Faisal II of Iraq E513833 entity
Predicate givenName P17 FINISHED
Object Faisal NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Faisal | Statement: [Faisal II of Iraq, givenName, Faisal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Faisal
Context triple: [Faisal II of Iraq, givenName, Faisal]
  • A. Faisal chosen
    Faisal is a male given name of Arabic origin, historically borne by several notable Middle Eastern leaders and royals.
  • B. Fuad
    Fuad is a character in the Italian romantic comedy film "The Tiger and the Snow," which blends humor and drama against the backdrop of the Iraq War.
  • C. Muhammad Ibrahim
    Muhammad Ibrahim, better known as Sardar Muhammad Ibrahim Khan, was a prominent Kashmiri political leader and the founding President of Azad Jammu and Kashmir.
  • D. Shah Karim al-Husayni
    Shah Karim al-Husayni, known as Aga Khan IV, is the 49th hereditary Imam of the Nizari Ismaili Muslims and a prominent philanthropist and spiritual leader.
  • E. Husayni
    Husayni is a variant of the prominent Palestinian family name al-Husseini, historically associated with notable religious and political leaders in Jerusalem.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0b4f675cc8190b4e745225b62eb66 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c4624ce48190b85e5bb24cf0a305 completed April 21, 2026, 12:27 a.m.
Created at: April 16, 2026, 12:45 p.m.